Skills/audit/SKILL.md

---
name: audit
description: Use at cycle close OR when baseline drift is suspected. Runs architect drift review against the design ledger plus the configured regression scripts. Mandatory at every cycle close; deferral requires an explicit backlog issue naming the reason and the re-run date.
---

# audit — cycle-close tidy

> **Violating the letter of these rules is violating the spirit.**

## Overview

Without a scheduled clean-up step, codebases grow by accretion:
every iteration adds, none tear out, and deferred drift
compounds across cycles. This skill is the cleanup step. It
runs after the last iteration of a cycle closes and before the
next cycle starts.

## When to Use / Skipping

**Mandatory** at every cycle close. Skipping requires an
explicit backlog issue (the project's issue tracker — its
CLAUDE.md project facts) naming:

- the blocking sibling cycle (if any),
- the reason for deferral,
- the date the audit will be re-run.

"We want to keep moving" is not a valid reason.

Also triggered manually when baseline drift is suspected
outside a cycle close (e.g. the bencher reports an unexplained
metric shift).

## The Iron Law

```
TIDY IS NON-OPTIONAL AT CYCLE CLOSE
REGRESSION-SCRIPT EXIT CODE 2 = FIX INFRASTRUCTURE FIRST, NEVER REPORT AS REGRESSION
NO BASELINE UPDATE WITHOUT A PAIRED RATIFY STATEMENT IN THE AUDIT COMMIT BODY
```

## The Process

### Step 1 — Architect drift review

Dispatch `architect` with the cycle scope (commit range from
the previous cycle-close to `HEAD`):

```
For cycle <X>: read the project's design ledger, if it has one
(its CLAUDE.md project facts), walk its contracts;
`git log <prev-close>..HEAD --format=full` for the cycle's
iter and audit commit bodies; `git diff <prev-close>..HEAD`
for the diff; report drift.
```

Architect produces a prioritised drift list (see
`agents/architect.md` output format).

### Step 2 — Regression check

Run the project's regression command(s) (its CLAUDE.md project
facts), in order. If there are none, the project has no
regression gate and this step is a no-op (architect remains the
gate).

The exit code of each script is the gate:

| Exit | Classification | Action |
|------|----------------|--------|
| `0` | Green | All metrics within tolerance vs. the script's baseline. The cycle's drift gate is clear (drift-clean, not a milestone close — see `../docs/pipeline.md` § Milestone-close gate). |
| `1` | Drift / regression | At least one metric regressed past tolerance. Treat like a drift item. |
| `2` | Infrastructure failure | Script-output format changed, fixture missing, or harness can't spawn. **Fix the infrastructure FIRST**, re-run. Never claim a regression on exit 2. |

A non-zero exit on any script in the list triggers the bencher
(`agents/bencher.md`) for hypothesis-driven diagnostics if the
regression needs localising.

### Step 3 — Classify and report

Combine architect drift items + regression results into one
report to the orchestrator. Each item is one of:

- **fix** (specific iter scoped, plan + implement)
- **ratify** (`--update-baseline` on the firing script + an
  explicit ratify statement in the audit commit body naming
  the iter that intentionally moved the metric and why)
- **carry-on** (architect found nothing actionable, regression
  green)

### Step 4 — Resolve

The orchestrator picks per item:

- **fix path:** dispatch `planner` + `implement` for a tidy
  iteration. The implement skill leaves the fix in the working
  tree; the orchestrator commits per the iter's pattern
  (suggested subject: `iter <X>.tidy: <fix>`).
- **ratify path:** run `--update-baseline` (or the equivalent)
  on the firing script. The audit-close commit carries both
  the updated baseline and a ratify paragraph in its body
  naming the iter that moved the metric and the substantive
  reason (semantic cost, intentional trade-off).
- **carry-on path:** the audit-close commit body says
  `cycle <X> tidy (clean)` and ratifies whatever the
  regression check drove. Here `clean` means *drift-clean* —
  the cycle's code matches the ledger; it is **not** a milestone
  close, which additionally requires a green milestone fieldtest
  (see `../docs/pipeline.md` § Milestone-close gate). Audit
  commits always exist at cycle close — they carry the architect
  findings, the regression numbers, and the resolution.

  A carry-on is honoured only with positive evidence the architect
  actually reviewed: a non-empty **What holds** in its report (the
  design commitments it confirmed it read). A bare `clean` with
  nothing held — especially when Step 2 was a no-op (no regression
  scripts, so the architect is the *sole* gate) — reads as an
  unreviewed run, not a clean cycle; re-dispatch rather than close
  on it. (The architect owes this itself — `agents/architect.md`
  Red Flags, "about to return clean without having read the diff in
  full"; the gate verifies it rather than trusting the status.)

## Handoff Contract

`audit` hands to the orchestrator:

| Field | Content |
|-------|---------|
| `holds` | architect's **What holds** — the 1-3 design commitments the cycle preserved (`agents/architect.md` Output format). Non-empty is the evidence-of-review the carry-on gate checks; an empty `holds` reads as an unreviewed run. |
| `drift_items` | prioritised list (path + 1-line justification) from architect |
| `regression_results` | per script: exit code + **raw output verbatim** (no rounding, no summarisation — the orchestrator second-guesses with the full numbers) |
| `recommendation` | per-item: `fix` / `ratify` / `carry-on` |

The orchestrator decides the per-item outcome; `audit` does
not self-resolve.

## Common Rationalisations

| Excuse | Reality |
|--------|---------|
| "Tidy can wait until next week, let's keep moving" | The project's CLAUDE.md is explicit: tidy at cycle close is non-optional. Deferral compounds; next cycle adds its own drift. |
| "Regression red, just bump the baseline, the regression is expected" | "Expected" is exactly the claim that needs evidence. Localise the regression, then either fix OR ratify with a paragraph in the audit commit body naming the iter and reason. |
| "Drift item is trivial, ignore it" | Trivial drift left open trains future-orchestrator to treat the architect's findings as advisory. Six items in, six items out. |
| "Regression scripts are hanging, skip them this cycle" | Exit code 2 = fix infrastructure FIRST. No skipping. |
| "Architect report is empty, fast-close" | Empty report is a possible outcome. Run the regression scripts anyway. Both gates must pass. |

## Red Flags — STOP

- Skipping any configured regression script
- Bumping baseline without a paired ratify statement in the audit commit body
- Treating exit code 2 as a regression to fix
- Closing a cycle with drift items in `pending` state
- "We'll re-run after the holidays" without a dated backlog issue
- Declaring a milestone closeable on the strength of an
  audit-clean while the milestone fieldtest has not run green —
  audit proves drift-clean, never functional (see
  `../docs/pipeline.md` § Milestone-close gate)

## Cross-references

- **Agents dispatched:**
  - `agents/architect.md` — drift review against the design
    ledger
  - `agents/bencher.md` — hypothesis-driven regression
    diagnostics when a metric needs localising
- **Hand-off target:** the orchestrator, or `../planner` +
  `../implement` for a tidy iteration.